Volumetric Image Visualization Alexandre Xavier Falc ao LIDS - - PowerPoint PPT Presentation

Volumetric Image Visualization Alexandre Xavier Falc˜ ao LIDS - Institute of Computing - UNICAMP afalcao@ic.unicamp.br Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Object delineation by optimum seed competition We have learned that multiple objects can be delineated by optimum seed competition. In this lecture, we will learn the general IFT algorithm for object delineation [6, 7, 13, 14]. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Object delineation by optimum seed competition We have learned that multiple objects can be delineated by optimum seed competition. In this lecture, we will learn the general IFT algorithm for object delineation [6, 7, 13, 14]. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Object delineation by optimum seed competition We have learned that multiple objects can be delineated by optimum seed competition. In this lecture, we will learn the general IFT algorithm for object delineation [6, 7, 13, 14]. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Object delineation by optimum seed competition Let ( D I , A ) be a graph derived from a 3D image ˆ I = ( D I , I ), such that A : { ( p , q ) ∈ D I × D I | � q − p � ≤ 1 } is a 6-neighborhood relation and A ( p ) is the set of adjacents of p . Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Object delineation by optimum seed competition Let ( D I , A ) be a graph derived from a 3D image ˆ I = ( D I , I ), such that A : { ( p , q ) ∈ D I × D I | � q − p � ≤ 1 } is a 6-neighborhood relation and A ( p ) is the set of adjacents of p . Let S ⊂ D I be a set of seed voxels, such that λ ( s ) ∈ { 0 , 1 , . . . , c } indicates that seed s ∈ S belongs to one object 1 ≤ i ≤ c or the background 0. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Object delineation by optimum seed competition Let ( D I , A ) be a graph derived from a 3D image ˆ I = ( D I , I ), such that A : { ( p , q ) ∈ D I × D I | � q − p � ≤ 1 } is a 6-neighborhood relation and A ( p ) is the set of adjacents of p . Let S ⊂ D I be a set of seed voxels, such that λ ( s ) ∈ { 0 , 1 , . . . , c } indicates that seed s ∈ S belongs to one object 1 ≤ i ≤ c or the background 0. Let f be a path-cost function, such that f ( � q � ) = H ( q ) f ( π p · � p , q � ) = max { f ( π p ) , w ( p , q ) } , where π p · � p , q � is the extension of a path π p = � p 1 , p 2 , . . . , p n = p � by an arc ( p , q ) ∈ A with weight w ( p , q ), � q � is a trivial path, and H ( q ) is a handicap function. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The general IFT algorithm For effective delineation, w ( p , q ) ≥ 0 should be lower inside the objects and higher across their boundaries. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The general IFT algorithm For effective delineation, w ( p , q ) ≥ 0 should be lower inside the objects and higher across their boundaries. H ( q ) is usually defined as 0 for q ∈ S and + ∞ , otherwise. Note, however, that seeds may have different priorities. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The general IFT algorithm For effective delineation, w ( p , q ) ≥ 0 should be lower inside the objects and higher across their boundaries. H ( q ) is usually defined as 0 for q ∈ S and + ∞ , otherwise. Note, however, that seeds may have different priorities. While minimizing a path-cost map C ( q ) = min ∀ π q ∈ Π { f ( π q ) } , where Π is the set of all possible paths, the IFT algorithm propagates paths from S in a non-decreasing order of costs and outputs an optimum-path forest rooted in S . Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The general IFT algorithm An optimum-path forest rooted in S is an acyclic map P of predecessors, such that P ( q ) = p ∈ D I \S , when p is the predecessor of q in the optimum path π q , and P ( q ) = nil �∈ D I , when q ∈ S . For instance: π c = � h , i , f , c � , P ( c ) = f , π a = � a � , and P ( a ) = nil . Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The general IFT algorithm Consider, for example, the image graph on the left, where the numbers indicate I ( q ) and A is a 4-neighborhood relation. On the right, the trivial forest for the path-cost function f with H ( q ) = I ( q ) + 5 and w ( p , q ) = I ( q ). In this case, the roots of the forest are defined by the time p is visited for possible optimum path extension and P ( p ) = nil . Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The general IFT algorithm At each iteration of | D I | iterations, the algorithm selects one node p , among those of lowest cost, never selected before, for possible optimum path extension. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The general IFT algorithm At each iteration of | D I | iterations, the algorithm selects one node p , among those of lowest cost, never selected before, for possible optimum path extension. for each adjacent q ∈ A ( p ), such that C ( q ) > f ( π p · � p , q � ), it updates the maps C ( q ) ← f ( π p · � p , q � ) and P ( q ) ← p . Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The general IFT algorithm At each iteration of | D I | iterations, the algorithm selects one node p , among those of lowest cost, never selected before, for possible optimum path extension. for each adjacent q ∈ A ( p ), such that C ( q ) > f ( π p · � p , q � ), it updates the maps C ( q ) ← f ( π p · � p , q � ) and P ( q ) ← p . After iterations 1 (left) and 2 (right), we will have Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The general IFT algorithm After iterations 3 (left) and from 4–9 (right), we will have An optimum-path forest for the path-cost function f . Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The general IFT algorithm After iterations 3 (left) and from 4–9 (right), we will have An optimum-path forest for the path-cost function f . Its bottleneck is to determine, at each iteration, the node p ∈ D I of lowest cost, never selected before. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The IFT algorithm for object delineation Input: ˆ I = ( D I , I ), A , w , and S labeled by λ . Output: P , C , and a label map L , where L ( q ) is the label of the seed that has conquered q . Auxiliary: A priority queue Q and a variable tmp . 1 ∀ q ∈ D I , do 2 C ( q ) ← + ∞ and P ( q ) ← nil . 3 If q ∈ S then C ( q ) ← 0 and L ( q ) ← λ ( q ). 4 insert q in Q . 5 While Q � = ∅ do 6 Remove p = arg min q ∈ Q { C ( q ) } from Q . 7 ∀ q ∈ A ( p ), such that q ∈ Q , do 8 tmp ← max { C ( p ) , w ( p , q ) } . 9 If C ( q ) > tmp , then 10 C ( q ) ← tmp , P ( q ) ← p , and L ( q ) ← L ( p ). Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

The priority queue Q For w ( p , q ) ∈ [0 , K ], K ≪ | D I | , the algorithm executes in O ( | D I | ), using bucket sort . p 5 p 4 p 1 p 2 K−1 2 p 3 1 K 0 p 6 Nodes p ∈ D I are inserted and removed from bucket C ( p ) mod K + 1 in O (1). Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Arc-weight assignment The effectiveness of object delineation depends more on the arc-weight assignment w ( p , q ) than on the location of the seeds inside their objects (background). Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Arc-weight assignment The effectiveness of object delineation depends more on the arc-weight assignment w ( p , q ) than on the location of the seeds inside their objects (background). It should be clear that if w ( p , q ) is higher across the boundaries of the object than inside and outside it, any two seeds, one inside and one outside the object would be enough to complete segmentation. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Arc-weight assignment Pattern classifiers, such as deep neural networks, may be able to create an object map O such that the values O ( p ) are higher inside the object than in most parts of the background. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Arc-weight assignment Pattern classifiers, such as deep neural networks, may be able to create an object map O such that the values O ( p ) are higher inside the object than in most parts of the background. The object map O may be used for weighted arc orientation [13], when λ ( p ) ∈ { 0 , 1 } . G α ( q )  if O ( p ) > O ( q ) and L ( p ) = 1,   G α ( q ) if O ( p ) < O ( q ) and L ( p ) = 0,  w ( p , q ) = G β ( q ) if O ( p ) = O ( q ),   G ( q ) otherwise,  where α > 1, 0 < β < 1, G ( q ) the magnitude of a gradient vector � q − p 1 G ( p ) = � ∀ q ∈A ( p ) [ I ( q ) − I ( p )] � v pq , � v pq = � q − p � . |A ( p ) | Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization

Arc-weight assignment The method in this case may be called an oriented watershed transform. (a) (b) (a) Mediastinum and (b) traquea-bronchi extracted from a CT image of the thorax. Alexandre Xavier Falc˜ ao MO815 - Volumetric Image Visualization